Tourism information promotion method and device, equipment and storage medium

Abstract

The invention relates to the technical field of information pushing, in particular to a tourism information promotion method, device and equipment and a storage medium, and aims to generate an information propagation network and increase information sources by capturing each network page and network resource information in the Internet, and perform hotspot information mining on the information propagation network through a preset hotspot mining model to improve the information transmission efficiency. Therefore, the network hotspot information is identified, the ternary attribute information of the network hotspot information is extracted, the tourism promotion information is associated by utilizing the network hotspot information to the greatest extent, the promotion popularity of the tourism information is improved, and the technical problems of poor promotion effect and low conversion rate of the tourism information in the prior art are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of information push, and in particular to a method, device, equipment and storage medium for promoting tourism information. Background Art

[0002] With the development of society, more and more people choose to travel. In order to attract more tourists, various places generally choose to publish fishing-related tourism recommendation information on the Internet. However, there is a large amount of complex network information on the Internet. When promoting tourism information, the popularity of network resources is not utilized, the effect of tourism information promotion is not good, and the conversion rate is low.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a tourism information promotion method, device, equipment and storage medium, aiming to solve the technical problems of poor promotion effect and low conversion rate of tourism information in the prior art.

[0005] To achieve the above object, the present invention provides a method for promoting tourism information, which comprises the following steps:

[0006] Crawl web pages and network resource information to generate information dissemination networks;

[0007] Perform hotspot mining on the information dissemination network by using a preset hotspot mining model to obtain network hotspot information;

[0008] Extracting ternary attribute information of the network hotspot information;

[0009] The corresponding tourism promotion information is matched based on the ternary attribute information, and the tourism promotion information is pushed.

[0010] Optionally, the information dissemination network includes: information nodes and node edges, the information nodes are captured web pages, and the node edges are link relationships between web pages;

[0011] The hotspot mining of the information dissemination network is performed by using a preset hotspot mining model to obtain network hotspot information, including:

[0012] Determine a first hot spot information sorting result corresponding to a first information network by using a preset sorting model, wherein the first information network is constructed by the network page and the link relationship;

[0013] Determining a ranking result of second hot information corresponding to a second information network by a preset importance measurement model, wherein the second information network is constructed by the network page;

[0014] The network hotspot information is generated according to the first hotspot information sorting result and the second hotspot information sorting result.

[0015] Optionally, determining the sorting result of the first hot spot information corresponding to the first information network by using a preset sorting model includes:

[0016] Determining the coreness and near-coreness of each information node in the first information network;

[0017] Iterate each core degree and each approach core degree to obtain the core degree value of each information node;

[0018] The information nodes are sorted according to their coreness values ​​to obtain a first hot spot information sorting result.

[0019] Optionally, determining the ranking result of the second hot information corresponding to the second information network by using a preset importance measurement model includes:

[0020] Establishing an adjacency matrix of the second information network;

[0021] Determine the eigenvector value of each information node in the second information network based on the adjacent matrix;

[0022] The information nodes are sorted according to their characteristic vector values ​​to obtain a second hot spot information sorting result.

[0023] Optionally, matching corresponding tourism promotion information based on the ternary attribute information and pushing the tourism promotion information includes:

[0024] Determining the similarity between the ternary attribute information and the tourist hotspot information in the database;

[0025] When the similarity is greater than a preset similarity threshold, matching corresponding tourism promotion information based on the ternary attribute information;

[0026] Push the tourism promotion information.

[0027] Optionally, the matching corresponding tourism promotion information based on the ternary attribute information includes:

[0028] Extracting the attributes of each dimension and the corresponding attribute values ​​in the ternary attribute information;

[0029] Generate an attribute mapping vector and an attribute value mapping vector in the same vector space based on the attribute and the attribute value;

[0030] The attributes, attribute values, attribute mapping vectors of the same vector space, and attribute value mapping vectors of each dimension are aggregated through a preset aggregation model to obtain attribute information representation of each dimension;

[0031] According to the attribute information, it is determined that the ternary attribute information matches the corresponding tourism promotion information.

[0032] Optionally, the pushing of the tourism promotion information includes:

[0033] Sensing the promotion traffic resources through a sensor, wherein the sensor is at least one hot spot information in the initial solution space;

[0034] Aggregate and promote a traffic distributor based on the sensor;

[0035] Capture tourism promotion information in promotion flow resources through the sensor and the promotion flow distributor;

[0036] The tourism promotion information is pushed through the promotion traffic distributor based on a preset wolf pack distribution model.

[0037] In addition, to achieve the above-mentioned purpose, the present invention also proposes a tourism information promotion device, which includes:

[0038] The crawling module is used to crawl web pages and network resource information to generate an information dissemination network;

[0039] A mining module, used to perform hotspot mining on the information dissemination network through a preset hotspot mining model to obtain network hotspot information;

[0040] An extraction module, used to extract ternary attribute information of the network hotspot information;

[0041] The push module is used to match the corresponding tourism promotion information based on the ternary attribute information and push the tourism promotion information.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also proposes a tourism information promotion device, which includes: a memory, a processor, and a tourism information promotion program stored in the memory and executable on the processor, and the tourism information promotion program is configured to implement the steps of the tourism information promotion method described above.

[0043] In addition, to achieve the above-mentioned purpose, the present invention further proposes a storage medium, on which a tourism information promotion program is stored, and when the tourism information promotion program is executed by a processor, the steps of the tourism information promotion method described above are implemented.

[0044] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the tourism information promotion method described above are implemented.

[0045] One or more technical solutions proposed in the present invention have at least the following technical effects: The present invention discloses a method for promoting tourism information, which includes: capturing web pages and network resource information to generate an information dissemination network; performing hotspot mining on the information dissemination network through a preset hotspot mining model to obtain network hotspot information; extracting ternary attribute information of the network hotspot information; matching corresponding tourism promotion information based on the ternary attribute information, and pushing the tourism promotion information. Compared with the prior art, the present invention generates an information dissemination network by capturing various web pages and network resource information on the Internet to increase the source of information, and performs hotspot information mining on the information dissemination network through a preset hotspot mining model to identify network hotspot information, and then extracts the ternary attribute information of the network hotspot information to maximize the use of network hotspot information to associate tourism promotion information, thereby increasing the promotion popularity of tourism information and avoiding the technical problems of poor promotion effect and low conversion rate of tourism information in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0048] Figure 1 It is a flow chart of the first embodiment of the tourism information promotion method of the present invention;

[0049] Figure 2 It is a flow chart of the second embodiment of the tourism information promotion method of the present invention;

[0050] Figure 3 It is a flow chart of the third embodiment of the tourism information promotion method of the present invention;

[0051] Figure 4 It is a structural block diagram of the first embodiment of the tourism information promotion device of the present invention;

[0052] Figure 5 It is a structural diagram of a tourism information promotion device in a hardware operating environment involved in an embodiment of the present invention.

[0053] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0054] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0055] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0056] Based on this, the embodiment of the present invention provides a method for promoting tourism information. Figure 1 , Figure 1 The figure is a flow chart of a first embodiment of a method for promoting tourism information according to the present invention.

[0057] In this embodiment, the tourism information promotion method includes:

[0058] Step S10: Capture web pages and network resource information to generate an information dissemination network.

[0059] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, tourism information promotion, etc. The following takes tourism information promotion as an example to illustrate this embodiment and the following embodiments.

[0060] It should be understood that with the rapid development of the Internet, various types of information on the Internet are expanding at an exponential rate. In addition to traditional media such as newspapers and television news, the Internet has become a way for people to obtain information that they rely on more and more. Moreover, with the increasing impact of paper printing on the environment and the widespread popularity of computers, mobile phones and similar communication devices connected to broadband networks, Internet information, with its advantages of environmental protection, convenience and large amount of information, is likely to replace and eliminate these traditional information dissemination channels.

[0061] Most of the existing tourism promotion methods also adopt the method of publishing relevant tourism videos on the Internet and promoting tourism information through the Internet. However, due to the chaos of information on the Internet, the effective dissemination rate of promotional information or promotional activities is very low, which in turn causes the promotional information or promotional activities to occupy a large amount of network resources without achieving the expected results, resulting in low efficiency in the use of network resources and increasing the cost of tourism promotion.

[0062] Faced with the complex and vast amount of network information, the concept of network hotspots came into being. Network hotspots refer to the popular and popular topics and events on the Internet, which represent the interests of the vast majority of users in a specific period of time. In other words, the promotion efficiency of Internet information release is related to the hot spots of the current period; especially for the promotion of tourism information, the promotion effect of tourism information will be affected by network hotspots. For example: if there is a large-scale performance program in a certain place, the effect and conversion rate of tourism promotion in that place will be better than the promotion effect and conversion rate when there is no performance program.

[0063] Specifically, the process of crawling web pages and network resource information and generating an information dissemination network refers to using a crawler to crawl the page content corresponding to the Internet information source with relatively high attention, forming an information dissemination network with a page as a node and the link relationship as the edge. The information dissemination network mainly includes information such as the number of links in the page, the information crawled from the page, and the page-level score.

[0064] Step S20: Perform hotspot mining on the information dissemination network through a preset hotspot mining model to obtain network hotspot information.

[0065] It can be understood that the preset hot spot mining model refers to the comprehensive ranking of hot spot information based on the sorting algorithm and the importance measurement algorithm, so as to determine the network hot spots with higher popularity in the information dissemination network. Since the types of network resource information captured in a period of time are complex and the amount of data is large, in order to improve the effect of subsequent tourism information promotion, the popularity of each information node in the information dissemination network is sorted, so that the hot spot information with higher popularity can be determined, and then in the subsequent information promotion process, more conversion rates can be attracted.

[0066] Step S30: extracting the ternary attribute information of the network hotspot information.

[0067] Ternary attribute information refers to the tourism attribute information of online hot information in the three dimensions of timeliness, attention and dissemination, including but not limited to characteristics, scenery, culture and other attributes.

[0068] Specifically, extracting the ternary attribute information of the network hotspot information may be performing word segmentation extraction on the network hotspot information to obtain tourism attribute information in three dimensions: timeliness, attention, and spread.

[0069] Step S40: Matching corresponding tourism promotion information based on the ternary attribute information, and pushing the tourism promotion information.

[0070] It can be understood that the use of ternary attributes to extract and match hot spot information increases the ability to accurately identify and classify hot spot information, and improves the accuracy of tourism hot spot information. Compared with keyword matching in the prior art, the ternary attribute method can narrow the scope of matching and provide a matching template for subsequent investment and promotion.

[0071] This embodiment captures various web pages and network resource information on the Internet to generate an information dissemination network, increase the source of information, and mines hot spot information on the information dissemination network through a preset hot spot mining model, thereby identifying network hot spot information, and then extracting ternary attribute information of the network hot spot information to maximize the use of network hot spot information to associate tourism promotion information, thereby increasing the promotion popularity of tourism information and avoiding the technical problems of poor promotion effect and low conversion rate of tourism information in the prior art.

[0072] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , step S20 comprises:

[0073] Step S201: determining a first hot information sorting result corresponding to a first information network through a preset sorting model, wherein the first information network is constructed by the network pages and the link relationships.

[0074] Step S202: determining a ranking result of second hot information corresponding to a second information network by using a preset importance measurement model, wherein the second information network is constructed by the network page.

[0075] Step S203: Generate network hotspot information according to the first hotspot information sorting result and the second hotspot information sorting result.

[0076] It should be noted that the preset sorting model is used to rank hot information based on the first information network, and the preset importance measurement model is used to rank hot information based on the second information network. The first information network is constructed by the network pages and the link relationships, and the second information network is constructed by the network pages. Specifically, each page is used as a node, and the link relationship between pages is used as an edge to generate the first information network; the second information network is constructed by removing n pages with direct or indirect link relationships, that is, the second information network is the first information network without the link relationship.

[0077] Furthermore, the determining the sorting result of the first hot spot information corresponding to the first information network by using a preset sorting model includes:

[0078] Determining the coreness and near-coreness of each information node in the first information network;

[0079] Iterate each core degree and each approach core degree to obtain the core degree value of each information node;

[0080] The information nodes are sorted according to their coreness values ​​to obtain a first hot spot information sorting result.

[0081] In the specific implementation, an information network is established using pages and link relationships, the initial set s of the algorithm is constructed, the elements in s are any information nodes p of the information network, and the information link relationship set t is constructed:

[0082] t=s∪m∪n

[0083] Among them, m is the set of nodes linked to the node number, and n is the set of reference nodes;

[0084] Calculate the core degree p of all information nodes p in s c and approaching coreness p d , the calculation formulas of coreness and approaching coreness are:

[0085]

[0086] Among them, q m and q n They are the coreness of the mth node set and the approach coreness of the nth reference node.

[0087] Then iterate the core degree and approach core degree until p c and p d After the calculated coreness values ​​are sorted and output, the first hot spot information sorting result is obtained.

[0088] Furthermore, the determining the ranking result of the second hot information corresponding to the second information network by using a preset importance measurement model includes:

[0089] Establishing an adjacency matrix of the second information network;

[0090] Determine the eigenvector value of each information node in the second information network based on the adjacent matrix;

[0091] The information nodes are sorted according to their characteristic vector values ​​to obtain a second hot spot information sorting result.

[0092] In the specific implementation, the adjacent matrix A of the second information network is established. ij , calculate the eigenvector value of each information node i of the second information network:

[0093]

[0094] Among them, a ij=1 indicates that there is a direct connection between node i and node j, a ij = 0 means that there is no direct connection between node i and node j, and λ means that the eigenvector of matrix A is represented by e, that is, e = (e1, e2, ..., e u ).

[0095] The characteristic vector values ​​of each information node of the second information network are sorted in descending order and then output to obtain a second hot spot information sorting result.

[0096] According to the ranking results of the two algorithms with different weight ratios, the final hotspot mining results are obtained:

[0097] H=IP+(1-I)Q

[0098] Among them, H is the collection of network hot spot information, I is the weight coefficient of the sorting algorithm, P is the first hot spot information sorting result calculated by the sorting algorithm, and Q is the second hot spot information sorting result calculated by the importance measurement algorithm.

[0099] In the specific implementation, suppose there is an Internet website, which includes different information pages and the link relationship between these pages. By using the hot spot mining algorithm to find the most popular hot information, first, use the sorting algorithm to rank. An information network will be established, with each page as a node and the link relationship between pages as an edge, and then use the core degree and approaching core degree to calculate. For example, suppose there are three nodes, pages A, B, and C, calculate their core degrees and approaching core degrees, and finally, sort the obtained core degree values ​​to get the ranking results of the hot information.

[0100] Then use the importance measurement algorithm to measure, first build the information network and establish the adjacent matrix A to represent the direct connection relationship between nodes. Then calculate the eigenvector value of each page, sort the eigenvectors in descending order, and get the measurement results of hot information. Finally, according to the sorting results of the sorting algorithm and the importance measurement algorithm, according to different weight ratios, the final hot mining results are obtained, and the most relevant and popular hot information can be found for further promotion and analysis.

[0101] This embodiment determines the sorting result of the first hot information corresponding to the first information network through a preset sorting model, wherein the first information network is constructed by the network page and the link relationship; determines the sorting result of the second hot information corresponding to the second information network through a preset importance measurement model, wherein the second information network is constructed by the network page; generates network hot information according to the sorting result of the first hot information and the sorting result of the second hot information, and sorts the network hot information through two algorithms, so as to determine the hot information with the highest relevance and popularity, thereby improving the promotion effect and conversion rate of subsequent tourism promotion information.

[0102] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 3 , step S40 comprises:

[0103] Step S401: Determine the similarity between the ternary attribute information and the tourist hotspot information in the database.

[0104] Step S402: When the similarity is greater than a preset similarity threshold, the corresponding tourism promotion information is matched based on the ternary attribute information.

[0105] Step S403: Pushing the tourism promotion information.

[0106] It should be noted that determining the ternary attribute information refers to using an encoder to learn the characteristic information of the ternary attributes in the word respectively:

[0107]

[0108] in, as well as They represent the feature representation of the nth triple attribute in the input text data, W s , W o and W v They represent the training parameters in the ternary attribute perception process, and b s 、b o and b v It is the bias term in the ternary attribute perception process.

[0109] The ternary attributes of the tourism information hotspots in the preset library include: location-tourism related information-tourism related information features; specifically, after sorting the information hotspots, an information hotspot related to tourism information is searched in the information hotspots, and the information hotspot needs to meet the ternary attributes of the tourism information hotspots in the preset library, such as: X city-food-clay pot soup; if the first name in the information hotspot sorting is: X city-election-voting, the ternary attribute does not belong to the tourism related attribute, and thus, the information hotspot does not belong to the tourism related hotspot.

[0110] Furthermore, the matching of corresponding tourism promotion information based on the ternary attribute information includes:

[0111] Extracting the attributes of each dimension and the corresponding attribute values ​​in the ternary attribute information;

[0112] Generate an attribute mapping vector and an attribute value mapping vector in the same vector space based on the attribute and the attribute value;

[0113] The attributes, attribute values, attribute mapping vectors of the same vector space, and attribute value mapping vectors of each dimension are aggregated through a preset aggregation model to obtain attribute information representation of each dimension;

[0114] According to the attribute information, it is determined that the ternary attribute information matches the corresponding tourism promotion information.

[0115] It can be understood that the step of traffic promotion includes matching corresponding promotion information according to the ternary attributes of the network information hotspot, matching each attribute, wherein a single attribute information E i include:

[0116] Attsingle(E i )=f(W key a key +W val a val )

[0117] Among them, a key and a val They are E i The attributes and attribute values ​​of W key and W val is to key and a val The mapping vector mapped to the unified vector space is used to merge all attribute values ​​through the aggregation function to obtain E i The attribute information indicates:

[0118]

[0119] Among them, AGG is the aggregation function, Att(E i ) means Ei All attribute value sets are matched with local tourism information according to all attribute value sets, and corresponding relative attributes are proposed. For example, the ternary attributes of relevant tourism hotspot information collected in the video promotion platform some time ago are: City X-Food-Barbecue; if the local area needs to match the corresponding tourism information for promotion, it can be: Place-Attribute-Specialty Food, and the attribute information can be further limited to food.

[0120] In the specific implementation process, suppose that a web crawler data collection of tourism information hotspots is being carried out, and a hotspot information named "X City Food Festival" is found. First, attribute comparison is performed to determine whether it belongs to tourism-related information. The hot information "X City Food Festival" can be segmented and extracted to obtain ternary attributes: "Location-X City", "Tourism-related information-Food Festival", "Tourism-related information features-Rich special food". Now, these attributes are learned into feature information through the encoder. Next, a ternary attribute library of tourism information hotspots is preset, such as "Location-Tourism-related information-Tourism-related information features", "X City-Food-Special Food". In the preset database, it can be seen that "X City-Food-Special Food" is a ternary attribute about tourism information hotspots. Therefore, it is believed that the hot information "X City Food Festival" is in line with tourism-related information. After attribute comparison, the next step is the flow promotion step. Assuming that you want to promote local food activities based on this hot information, you can construct a single attribute information for the hot information "X City Food Festival": "Location-X City", "Attribute-Food Festival", "Special Food-Special Food", and then you can use the aggregation function to merge all attribute value sets to get the final attribute information representation. Based on this information, you can promote it locally and associate the "X City Food Festival" with local special food to attract tourists and diners.

[0121] Furthermore, the pushing of the tourism promotion information includes:

[0122] Sensing the promotion traffic resources through a sensor, wherein the sensor is at least one information hotspot in the initial solution space;

[0123] Aggregate and promote a traffic distributor based on the sensor;

[0124] Capture tourism promotion information in promotion flow resources through the sensor and the promotion flow distributor;

[0125] The tourism promotion information is pushed through the promotion traffic distributor based on a preset wolf pack distribution model.

[0126] The preset wolf pack allocation model refers to a resource allocation model in human society or economics, which generally improves overall efficiency and fairness by changing the resource allocation strategy.

[0127] In the specific implementation, the steps of promoting on the Internet include: sensing information hotspots. In the initial solution space, the information hotspot with the optimal objective function value is the tourism information that needs to be promoted, which is defined as the promotion traffic conversion rate that the product can achieve. The calculation formula is:

[0128] Conversion rate = (number of conversions / total promotion traffic) * 100%

[0129] The perceptron perceives the promotion traffic resources, and regards the best S_num information hotspots in the initial solution space except the leader as the perceptron. It searches for available promotion traffic resources in the solution space. S_num is randomly selected as an integer between [n / (α+1), n / α], and α is the perceptron scale factor.

[0130] Select the largest available promotion traffic resource and one that is greater than the current available promotion traffic resource Y i0 One step forward in the direction of:

[0131]

[0132] in, is the walking step length, h is the walking direction, p=1,2,...,h is the loop parameter, and the above walking behavior is repeated until there is a scouting wolf with a scent concentration Y i >Y lead , where Y i is the current wolf odor concentration, Y lead is the alpha wolf scent concentration, then sensor i replaces the alpha wolf and initiates the calling behavior, or reaches the maximum number of wandering times T max ,Among them, the information hotspot initiates the calling behavior ,means that the promotion traffic distributors around the information hotspot gathers toward the information hotspot with a larger step;

[0133]

[0134] in, is the position of the k-th generation group leader in the d-dimensional space, For the running stride length, is the k-th generation promotion flow distributor position, The location of the traffic distributor for the k+1th generation is generalized.

[0135] The promotion traffic distributor and the sensor jointly capture the promotion traffic resources;

[0136]

[0137] in, is the position of the resource in the d-dimensional space in the k-th generation promotion traffic resource space, and λ is a random number uniformly distributed between [-1,1].

[0138] In this embodiment, a wolf pack allocation algorithm is used to allocate promotion traffic. The wolf pack does not distribute prey evenly, but distributes it in a "reward according to merit, from strong to weak" manner, that is, the prey is first allocated to the strong wolf who first discovers and catches the prey, and then to the weak wolf (that is, reward according to merit, first strong then weak). Similarly, in this method, promotion traffic resources are allocated to hot tourist information first, so as to quickly form a promotion effect, thereby obtaining more promotion conversion rates.

[0139] In the specific implementation process, assuming that a certain place needs to promote local tourist attractions, the conventional technical means is to upload the local attractions, food, human environment, climate change and other tourism-related elements to the network information disclosure platform. Specifically, if the network platform is used for promotion, a corresponding short video is made according to the attractions, food, human environment, climate change and other tourism-related elements and uploaded to the network platform with text. However, if the local tourism-related elements are extensive, the cost of promoting each video is huge, and the promotion effect is not good. Assuming that the technical solution of this application is used for promotion, the steps are as follows:

[0140] Information collection: Use crawlers to crawl the page content corresponding to the Internet information sources with relatively high popularity, forming a network diagram with pages as nodes and links as edges, which mainly includes the number of links in the page, the information crawled from the page, the page-level score, etc.

[0141] Hotspot mining: Using the web page graph obtained by the crawler, the information network pages are taken as nodes and the link relationships as edges to construct an information dissemination network that conforms to the network characteristics, and the hotspot mining algorithm is used to obtain network information hotspots; in this step, the hot video pages on the network platform are captured. The hot video pages are used as a hot information dissemination network based on the number of information plays, the number of citations, and the number of similar videos, and the network information hotspots are obtained according to the hotspot mining algorithm.

[0142] Attribute comparison: perform word segmentation extraction on network information hotspots, obtain the ternary attributes of network information hotspots, and perform similarity comparison with tourism information hotspots in the preset library. If the similarity is greater than the preset threshold, the network information hotspot belongs to tourism information hotspots. The network information hotspots mined on the network platform are ranked first as the current news "AB War", the second as the entertainment news "A Certain Artist's House Collapse", and the third as the fog video on the top of X Mountain. According to word segmentation extraction, these network information hotspots are processed respectively to obtain "AB--War--Event", "Artist--House Collapse--Event", "X Mountain--Scenery--Clouds and Fog". Since the specific events are not described in detail, the events are replaced by events. They can be as specific as "AB--War--Location", "AB--War--Casualties", which are determined by the specific news broadcast information. According to the ternary attributes extracted by word segmentation, the network information hotspots ranked first and second are excluded, which do not belong to tourism information hotspots. According to the third-ranked "X Mountain--Scenery--Clouds and Fog", the local tourism-related elements "Mountain--Scenery--Climate" are corresponding.

[0143] Traffic promotion: Match the corresponding promotion information according to the ternary attributes of network information hotspots and promote them on the Internet. After obtaining the corresponding ternary attributes, for example, the tourism-related elements corresponding to "mountain" include Mountain A, Mountain B, Mountain C, etc., and further matching the related elements can obtain "Mount A--Scenery--Climate". According to this ternary attribute, the corresponding video is selected and promoted. For example, the promotional videos of Mountain A include "Mount A--Hiking--Night Climbing", "Mount A--Hiking--Camping", "Mount A--Scenery--Hiking", and "Mount A--Scenery--Fog". Here, according to the ternary attributes of network hotspots, the video of "Mount A--Scenery--Fog" is selected for promotion. Promotional materials can be designed in a targeted manner, and effective online advertising and promotion activities can be carried out through channels such as the Internet and social media. With the help of intelligent algorithms for the allocation and optimization of promotional resources, tourists from different regions and interests can be attracted to visit, thereby promoting the development of local tourism.

[0144] This embodiment determines the similarity between the ternary attribute information and the tourist hotspot information in the database; when the similarity is greater than a preset similarity threshold, matches the corresponding tourist promotion information based on the ternary attribute information; and pushes the tourist promotion information.

[0145] This application also provides a tourism information promotion device, please refer to Figure 4 , the tourism information promotion device comprises:

[0146] The crawling module 10 is used to crawl network pages and network resource information to generate an information dissemination network.

[0147] The mining module 20 is used to perform hotspot mining on the information dissemination network through a preset hotspot mining model to obtain network hotspot information.

[0148] The extraction module 30 is used to extract the ternary attribute information of the network hotspot information.

[0149] The push module 40 is used to match the corresponding tourism promotion information based on the ternary attribute information and push the tourism promotion information.

[0150] This embodiment determines the sorting result of the first hot information corresponding to the first information network through a preset sorting model, wherein the first information network is constructed by the network page and the link relationship; determines the sorting result of the second hot information corresponding to the second information network through a preset importance measurement model, wherein the second information network is constructed by the network page; generates network hot information according to the sorting result of the first hot information and the sorting result of the second hot information, and sorts the network hot information through two algorithms, so as to determine the hot information with the highest relevance and popularity, thereby improving the promotion effect and conversion rate of subsequent tourism promotion information.

[0151] In one embodiment, the mining module 20 is also used to determine a first information hotspot ranking result corresponding to a first information network through a preset ranking model, wherein the first information network is constructed by the network page and the link relationship; determine a second information hotspot ranking result corresponding to a second information network through a preset importance measurement model, wherein the second information network is constructed by the network page; and generate network hotspot information based on the first information hotspot ranking result and the second information hotspot ranking result.

[0152] In one embodiment, the mining module 20 is also used to determine the coreness and approach coreness of each information node in the first information network; iteratively process each coreness and each approach coreness to obtain the coreness value of each information node; and sort the information nodes according to their coreness values ​​to obtain the first information hotspot sorting result.

[0153] In one embodiment, the mining module 20 is also used to establish an adjacent matrix of the second information network; determine the characteristic vector value of each information node in the second information network based on the adjacent matrix; and sort the information nodes according to the characteristic vector value to obtain a second information hotspot sorting result.

[0154] In one embodiment, the push module 40 is also used to determine the similarity between the ternary attribute information and the tourist hotspot information in the database; when the similarity is greater than a preset similarity threshold, match the corresponding tourist promotion information based on the ternary attribute information; and push the tourist promotion information.

[0155] In one embodiment, the push module 40 is also used to extract the attributes and corresponding attribute values ​​of each dimension in the ternary attribute information; generate attribute mapping vectors and attribute value mapping vectors of the same vector space based on the attributes and the attribute values; aggregate the attributes, attribute values, attribute mapping vectors and attribute value mapping vectors of each dimension in the same vector space through a preset aggregation model to obtain attribute information representation of each dimension; determine the tourism promotion information corresponding to the matching of the ternary attribute information according to the attribute information representation.

[0156] In one embodiment, the push module 40 is also used to sense promotion traffic resources through a sensor, where the sensor is at least one information hotspot in the initial solution space; aggregate promotion traffic distributors based on the sensor; capture tourism promotion information in promotion traffic resources through the sensor and the promotion traffic distributor; and push the tourism promotion information through the promotion traffic distributor based on a preset wolf pack distribution model.

[0157] The present application provides a tourism information promotion device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the tourism information promotion method in the above-mentioned embodiment one.

[0158] Reference below Figure 5 , which shows a schematic diagram of the structure of a tourism information promotion device suitable for implementing the embodiment of the present application. The tourism information promotion device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The tourism information promotion device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0159] like Figure 5As shown, the tourism information promotion device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the tourism information promotion device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the tourist information promotion device to communicate wirelessly or wired with other devices to exchange data. Although the tourist information promotion device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0160] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0161] The tourism information promotion device provided by the present application adopts the tourism information promotion method in the above embodiment, which can solve the technical problems of tourism information promotion. Compared with the prior art, the beneficial effects of the tourism information promotion device provided by the present application are the same as the beneficial effects of the tourism information promotion method provided by the above embodiment, and other technical features in the tourism information promotion device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0162] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0163] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0164] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the tourism information promotion method in the above-mentioned embodiment.

[0165] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0166] The computer-readable storage medium may be included in the tourism information promotion device; or may exist independently without being assembled into the tourism information promotion device.

[0167] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the tourism information promotion device, the tourism information promotion device can promote tourism information.

[0168] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0169] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0170] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0171] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned tourism information promotion method, and can solve the technical problems of tourism information promotion. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the tourism information promotion method provided in the above-mentioned embodiment, and will not be repeated here.

[0172] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned tourism information promotion method when executed by a processor.

[0173] The computer program product provided by this application can solve the technical problem of tourism information promotion. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the tourism information promotion method provided by the above embodiment, which will not be repeated here.

[0174] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for promoting tourism information, characterized in that: The tourism information promotion method comprises: Crawl web pages and network resource information to generate information dissemination networks; Perform hotspot mining on the information dissemination network by using a preset hotspot mining model to obtain network hotspot information; Extracting ternary attribute information of the network hotspot information; The corresponding tourism promotion information is matched based on the ternary attribute information, and the tourism promotion information is pushed.

2. The method according to claim 1, characterized in that The information dissemination network includes: information nodes and node edges, the information nodes are captured web pages, and the node edges are link relationships between web pages; The hotspot mining of the information dissemination network is performed by using a preset hotspot mining model to obtain network hotspot information, including: Determine a first hot spot information sorting result corresponding to a first information network by using a preset sorting model, wherein the first information network is constructed by the network page and the link relationship; Determining a ranking result of second hot information corresponding to a second information network by a preset importance measurement model, wherein the second information network is constructed by the network page; The network hotspot information is generated according to the first hotspot information sorting result and the second hotspot information sorting result.

3. The method according to claim 2, characterized in that The determining the sorting result of the first hot information corresponding to the first information network by using a preset sorting model includes: Determining the coreness and near-coreness of each information node in the first information network; Iterate each core degree and each approach core degree to obtain the core degree value of each information node; The information nodes are sorted according to their coreness values ​​to obtain a first hot spot information sorting result.

4. The method according to claim 2, characterized in that The determining the ranking result of the second hot information corresponding to the second information network by using a preset importance measurement model includes: Establishing an adjacency matrix of the second information network; Determine the eigenvector value of each information node in the second information network based on the adjacent matrix; The information nodes are sorted according to their characteristic vector values ​​to obtain a second hot spot information sorting result.

5. The method according to claim 1, characterized in that The matching of corresponding tourism promotion information based on the ternary attribute information and pushing the tourism promotion information includes: Determining the similarity between the ternary attribute information and the tourist hotspot information in the database; When the similarity is greater than a preset similarity threshold, matching corresponding tourism promotion information based on the ternary attribute information; Push the tourism promotion information.

6. The method according to claim 5, characterized in that The matching of corresponding tourism promotion information based on the ternary attribute information includes: Extracting the attributes of each dimension and the corresponding attribute values ​​in the ternary attribute information; Generate an attribute mapping vector and an attribute value mapping vector in the same vector space based on the attribute and the attribute value; The attributes, attribute values, attribute mapping vectors of the same vector space, and attribute value mapping vectors of each dimension are aggregated through a preset aggregation model to obtain attribute information representation of each dimension; According to the attribute information, it is determined that the ternary attribute information matches the corresponding tourism promotion information.

7. The method according to claim 5, characterized in that The pushing of the tourism promotion information includes: Sensing the promotion traffic resources through a sensor, wherein the sensor is at least one hot spot information in the initial solution space; Aggregate and promote a traffic distributor based on the sensor; Capture tourism promotion information in promotion flow resources through the sensor and the promotion flow distributor; The tourism promotion information is pushed through the promotion traffic distributor based on a preset wolf pack distribution model.

8. A tourism information promotion device, characterized in that: The tourism information promotion device comprises: The crawling module is used to crawl web pages and network resource information to generate an information dissemination network; A mining module, used to perform hotspot mining on the information dissemination network through a preset hotspot mining model to obtain network hotspot information; An extraction module, used to extract ternary attribute information of the network hotspot information; The push module is used to match the corresponding tourism promotion information based on the ternary attribute information and push the tourism promotion information.

9. A tourism information promotion device, characterized in that: The tourism information promotion device comprises: a memory, a processor and a tourism information promotion program stored in the memory and executable on the processor, wherein the tourism information promotion program is configured to implement the steps of the tourism information promotion method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a tourism information promotion program, and when the tourism information promotion program is executed by the processor, the steps of the tourism information promotion method according to any one of claims 1 to 7 are implemented.

Images